English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning-based 3D human pose estimation performs best when trained onlarge amounts of labeled data, making combined learning from many datasets animportant research direction. One obstacle to this endeavor are the differentskeleton formats provided by different datasets, i.e., they do not label thesame set of anatomical landmarks. There is little prior research on how to bestsupervise one model with such discrepant labels. We show that simply usingseparate output heads for different skeletons results in inconsistent depthestimates and insufficient information sharing across skeletons. As a remedy,we propose a novel affine-combining autoencoder (ACAE) method to performdimensionality reduction on the number of landmarks. The discovered latent 3Dpoints capture the redundancy among skeletons, enabling enhanced informationsharing when used for consistency regularization. Our approach scales to anextreme multi-dataset regime, where we use 28 3D human pose datasets tosupervise one model, which outperforms prior work on a range of benchmarks,including the challenging 3D Poses in the Wild (3DPW) dataset. Our code andmodels are available for research purposes.

Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats